metadata

license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_keras_callback
model-index:
  - name: whisper_charsplit_new_round2__0019
    results: []

whisper_charsplit_new_round2__0019

This model is a fine-tuned version of openai/whisper-tiny on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 0.0003
Train Accuracy: 0.0795
Train Wermet: 9.0084
Validation Loss: 0.5571
Validation Accuracy: 0.0769
Validation Wermet: 8.1563
Epoch: 18

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
training_precision: float32

Training results

Train Loss	Train Accuracy	Train Wermet	Validation Loss	Validation Accuracy	Validation Wermet	Epoch
0.0010	0.0795	8.7507	0.5575	0.0767	7.6778	0
0.0013	0.0795	8.9468	0.5652	0.0766	8.3360	1
0.0025	0.0795	8.7338	0.5673	0.0765	8.3770	2
0.0019	0.0795	8.9450	0.5623	0.0766	7.7117	3
0.0011	0.0795	8.9053	0.5609	0.0767	7.5155	4
0.0012	0.0795	8.8862	0.5667	0.0767	8.2913	5
0.0009	0.0795	8.7510	0.5642	0.0766	7.9083	6
0.0037	0.0795	9.3428	0.5717	0.0764	8.2631	7
0.0031	0.0795	9.2135	0.5636	0.0766	8.2384	8
0.0011	0.0795	8.9730	0.5605	0.0767	8.3958	9
0.0005	0.0795	9.3749	0.5552	0.0768	8.0800	10
0.0003	0.0795	9.3340	0.5584	0.0768	8.1322	11
0.0005	0.0795	9.2292	0.5687	0.0767	8.5576	12
0.0037	0.0795	9.2838	0.5751	0.0765	7.4189	13
0.0038	0.0795	8.7270	0.5605	0.0767	7.7098	14
0.0012	0.0795	8.8259	0.5563	0.0768	8.2647	15
0.0005	0.0795	9.0553	0.5620	0.0768	8.5020	16
0.0004	0.0795	9.1734	0.5607	0.0768	8.0252	17
0.0003	0.0795	9.0084	0.5571	0.0769	8.1563	18

Framework versions

Transformers 4.32.0.dev0
TensorFlow 2.12.0
Tokenizers 0.13.3